Station deployment design system, station deployment design device, station deployment design method, and program

Abstract

The present invention provides a station deployment design system which can perform appropriate base station arrangement for an entire wireless area and reduce the amount of computation compared to a full search. The station deployment design system is a station deployment design system for designing the installation position of a base station for constructing a wireless area, wherein the installation state of the base station is expressed as a binary value for each candidate point of the installation position of the base station, a plurality of candidates for the installation state of the base station is prepared for every candidate point, the candidates for the installation state of the base station are evaluated using an objective function including the coverage rate of a terminal and the number of base station installations, generational change is carried out by adding processes for selection, crossover, and mutation using a genetic algorithm, and an update process of the candidates for the installation state of the base station is performed to calculate a station deployment design result.

Description

Station placement design system, station placement design device, station placement design method, and program

[0001] The present invention relates to a station placement design system, a station placement design device, a station placement design method, and a program.

[0002] There are station location design systems that design the installation locations of wireless base stations to build wireless coverage areas. For example, a method has been proposed in which wireless station location design is performed based on communication quality and cost by combining multiple wireless systems (see, for example, Non-Patent Document 1).

[0003] Furthermore, station placement design is a combinatorial optimization problem, and various methods have been proposed as methods for solving combinatorial optimization problems. For example, evolutionary algorithms inspired by evolutionary mechanisms such as reproduction, mutation, genetic recombination, natural selection, and survival of the fittest have been proposed as population-based metaheuristic optimization algorithms (see, for example, Non-Patent Document 2).

[0004] Toshiro Nakahira, Daisuke Murayama, Satoshi Takatani, Kenichi Kawamura, Takatsugu Moriyama, "Multi-Wireless Area Design Method Based on Communication Capacity and Base Station Cost," IEICE Techniques, IEICE General Conference, B-5-97, Mar. 2022. Shota Yagami and Susumu Kuwashima, "Evolutionary Algorithms," Intelligent System Design Laboratory, 152nd Monthly Conference, April 2014.

[0005] In the conventional technology disclosed in Non-Patent Document 1, base stations are selected and placed one by one from among base station installation candidates using a greedy method, which poses the problem that appropriate base station placement cannot always be achieved throughout the entire wireless area. As a solution to this problem, a method of performing an exhaustive search to find the optimal base station installation location from among the base station installation candidates can be considered, but this poses the problem that the amount of calculation increases as the number of base station installation candidates increases.

[0006] The embodiments of the present invention have been made in view of the above-mentioned problems, and provide a station placement design system that can appropriately place base stations in the entire wireless area and reduce the amount of calculation compared to a full search.

[0007] In order to solve the above problems, a station location design system according to an embodiment of the present invention is a station location design system that designs the installation positions of base stations for constructing a wireless area, and expresses the installation state of the base station as a binary value for each candidate point of the installation position of the base station, prepares multiple candidates for the installation state of the base station for all candidate points, evaluates the candidates for the installation state of the base station using an objective function that includes the terminal coverage rate and the number of installed base stations, and performs selection, crossover, and mutation processes using a genetic algorithm to proceed with generational change, and calculates the station location design result by updating the candidates for the installation state of the base station.

[0008] According to an embodiment of the present invention, it is possible to provide a station placement design system that can appropriately place base stations in the entire wireless area and reduce the amount of calculation compared to a full search.

[0009] FIG. 1 is a diagram showing an example of the configuration of a station placement design system according to the present embodiment; FIG. 2 is a flowchart showing an example of station placement design processing according to the present embodiment; FIG. 3 is a diagram showing an image of a design target area according to the present embodiment; FIG. 4 is a diagram for explaining tournament selection; FIG. 5 is a diagram for explaining uniform crossover; FIG. 6 is a diagram showing an example of a result display screen according to the present embodiment; and FIG. 7 is a diagram showing an example of the hardware configuration of a computer according to the present embodiment.

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The embodiment described below is merely an example, and the embodiment to which the present invention is applied is not limited to the following embodiment.

[0011] <Configuration Example of Station Placement Design System> Fig. 1 is a diagram showing a configuration example of a station placement design system according to this embodiment. The station placement design system 1 is a system that performs station placement design, which designs appropriate installation positions of wireless base stations for constructing a wireless area, based on input design conditions. In the example of Fig. 1, the station placement design system 1 includes a station placement design device 100 and a terminal device 110 that can communicate with the station placement design device 100.

[0012] The station placement design device 100 is an information processing device having a computer configuration, or a system including multiple computers. The station placement design device 100 realizes each functional configuration shown in Fig. 1 by, for example, a computer included in the station placement design device 100 executing a program stored in a storage medium. In the example of Fig. 1, the station placement design device 100 has each functional configuration such as a communication unit 101, an input / output unit 102, a station placement design unit 103, and a storage unit 104. Note that at least a portion of each of the above functional configurations may be realized by hardware.

[0013] The communication unit 101 executes a communication process for communicating with other devices such as the terminal device 110. For example, the communication unit 101 transmits and receives data to and from the terminal device 110 via a communication network such as a wide area network (WAN) and / or a local area network (LAN).

[0014] The input / output unit 102 performs, for example, input processing to accept input of design conditions and the like from the terminal device 110, and output processing to output a result display screen that displays the station placement design results by the station placement design device 100 to the terminal device 110.

[0015] The station location design unit 103 executes station location design processing to design appropriate installation positions of wireless base stations for establishing a wireless area based on the input design conditions.

[0016] The storage unit 104 stores, for example, the design conditions received by the input / output unit 102, the station placement design results designed by the station placement design unit 103, and various data used during the station placement design.

[0017] (Processing Overview) Because there are limits to the range of radio waves from a wireless base station (hereinafter referred to as a base station) and the number of terminals that a single base station can accommodate, if there are not enough base stations installed, the area coverage and terminal accommodation will be insufficient. On the other hand, if there are too many base stations installed, the cost of the base stations themselves, as well as installation and operation costs, will increase, resulting in inefficiency. Therefore, it is important to design base stations so that the necessary number of base stations can be installed in appropriate locations.

[0018] For example, in a conventional station placement design method such as that shown in Non-Patent Document 1, base stations are selected and placed one by one from among base station placement candidates, for example, using a greedy method, which may result in inappropriate placement of base stations across the entire wireless area. As a countermeasure, a method of performing an exhaustive search to find the optimal base station placement location from among the base station placement location candidates may be considered, but this results in a problem of increased computational complexity as the number of base station placement candidates increases.

[0019] Therefore, the station location design system 1 according to this embodiment expresses the installation status of a base station for each candidate point for the installation location of the base station as a binary value such as [0, 1], and regards the installation status of the base station for all candidate points as genes. For example, 0 indicates that a base station is not installed at the candidate point, and 1 indicates that a base station is installed at the candidate point. In this way, the station location design system 1 prepares multiple candidates for the installation status of the base station for all candidate points. The station location design system 1 also evaluates the candidates for the installation status of the base station as an objective function including the terminal coverage rate and the number of installed base stations. Furthermore, the station location design system 1 uses a multi-objective genetic algorithm to perform selection, crossover, and mutation processes to advance generational changes, and calculates the station location design results by updating the candidates for the installation status of the base station.

[0020] As a result, according to the station placement design system 1 of this embodiment, a globally optimal solution can be obtained compared to the greedy method (less likely to fall into a local solution), and the amount of calculation can be significantly reduced compared to the full search.

[0021] As described above, according to this embodiment, it is possible to provide a station placement design system that can appropriately place base stations in the entire wireless area and reduce the amount of calculation compared to a full search.

[0022] The configuration of the station placement design system 1 shown in Fig. 1 is an example. For example, the functions of the station placement design device 100 may be distributed among multiple information processing devices. At least a part of the processing performed by the station placement design unit 103 may be realized by a cloud service or a program executed by a virtual machine on the cloud. Furthermore, the station placement design device 100 may input design conditions and display a screen showing the results of the station placement design without using the terminal device 110.

[0023] <Processing Flow> Next, the processing flow of the station placement design method according to this embodiment will be described.

[0024] 2 is a flowchart showing an example of the station placement design process according to this embodiment. This process shows a specific example of the station placement design process executed by the station placement design system 1 described with reference to FIG.

[0025] In step S201, the station placement design unit 103 sets a design target area. As an example, the station placement design unit 103 sets the design target area 300 indoors where a plurality of shielding objects 301 are arranged, as shown in Fig. 3. The design target area 300 set by the station placement design unit 103 has three-dimensional coordinates based on, for example, three-dimensional CAD data or three-dimensional data acquired by a three-dimensional sensor.

[0026] In step S202, the station location design unit 103 places multiple evaluation points (hereinafter referred to as terminals 302) for evaluating wireless quality such as received power within the set design target area 300, for example, as shown in FIG. 3. The station location design unit 103 also places multiple candidate points 303, which are candidates for base station installation locations, within the design target area 300, for example, as shown in FIG. 3. Furthermore, the station location design unit 103 calculates the received power that each terminal 302 receives from the base station installed at each candidate point 303. For example, the station location design unit 103 uses a known radio wave propagation simulation technique such as ray tracing to calculate the received power that each terminal 302 receives when a base station is installed at each candidate point 303.

[0027] In step S203, the station placement design unit 103 generates an initial population. For example, the station placement design unit 103 randomly generates multiple station placement design patterns. The station placement design unit 103 also expresses whether or not a base station is to be placed at a candidate point 303 as [0, 1], regards the installation status of the base station for each candidate point 303 as a gene, and executes the processes from step S204 onwards. It is also possible to set the size of the gene to the number of installed base stations and optimize the base station numbers (e.g., 1 to 28) to be placed, but this would reduce the convergence of the evolutionary algorithm.

[0028] In step S204, the station placement design unit 103 evaluates the generated station placement design patterns (hereinafter referred to as populations) using an objective function including the terminal coverage rate and the number of installed base stations. For example, the station placement design unit 103 evaluates the generated population using the objective function shown in the following equation (1).

[0029] Here, α and μ are coefficients. The terminal coverage rate is, for example, a value indicating the proportion of terminals 302 that achieve the target received power among multiple terminals 302. The number of base stations to be installed is, for example, the number of base stations to be installed in the design area 300.

[0030] The objective function of equation (1) sets the terminal coverage rate as "+" and the number of installed base stations as "-". As a result, by maximizing the objective function of equation (1), the terminal coverage rate increases while the number of installed base stations decreases.

[0031] In station placement design, the terminal coverage rate and the number of base stations to be installed are basically in an inverse relationship, but in this embodiment, by setting the number of base stations to be installed as "-", both the terminal coverage rate and the number of base stations to be installed are included in a single objective function.

[0032] This process can be expressed as an optimization problem mathematically using the objective function of the following equation (2) and the constraint condition of the following equation (3), for example.

[0033] subject to

[0034] Equation (2) is the objective function corresponding to equation (1), and equation (3) is the constraint. In addition, i is a terminal ∀i∈I, j is a base station ∀j∈J, n is a station placement design plan ∀n∈N, α and μ are coefficients, r ｉｊ is the received power that terminal i receives from base station j, p ｉ，ｎ is the maximum received power that terminal i receives in channel placement plan n, p ｔ is the target received power, z ｉ，ｎ is the degree of achievement of the target received power, and P is the number of base stations to be installed in the station placement design plan n, which corresponds to the penalty function in the objective function.

[0035] In step S205, the station placement design unit 103 saves the elites. For example, the station placement design unit 103 stores the top individuals in the storage unit 104 or the like in order to pass them on to the next generation based on the evaluation using the objective function. This ensures that the optimal solution is always updated in the correct direction. In addition, the station placement design unit 103 executes the processes of steps S206 to S208 in parallel with the process of step S205.

[0036] In step S206, the station placement design unit 103 performs a selection operation on the population. For example, the station placement design unit 103 performs a tournament selection to select a top-ranked station from a randomly selected population. Note that the tournament selection is an example of a selection operation performed by the station placement design unit 103.

[0037] FIG. 4 is a diagram for explaining tournament selection. As an illustrative example, assume that there are six populations, (A) to (F), as shown in FIG. 4. For example, when individuals (A), (B), and (C) are randomly selected from populations (A) to (F), the station placement design unit 103 selects the individual (A) with the highest score. Similarly, when individuals (C), (E), and (F) are randomly selected from populations (A) to (F), the station placement design unit 103 selects the individual (C) with the highest score. By performing such a selection operation, the station placement design unit 103 can diversify solutions and reduce the risk of falling into a local solution.

[0038] In step S206, the station placement design unit 103 performs a crossover operation on the population. For example, the station placement design unit 103 performs uniform crossover, which randomly replaces all genes. Note that uniform crossover is an example of a crossover operation performed by the station placement design unit 103.

[0039] 5 is a diagram for explaining uniform crossover. As an illustrative example, when there are (parent A) and (parent B) as shown in FIG. 5, the station placement design unit 103 randomly swaps (parent A) and (parent B) to generate (child A) and (child B). By such crossover processing, the station placement design unit 103 can diversify the solutions.

[0040] In step S208, the station placement design unit 103 performs a mutation operation on the population, which significantly changes the individuals with a certain probability. This allows the station placement design unit 103 to reduce the risk of falling into a local solution.

[0041] In step S209, the station placement design unit 103 forms a next generation population. Also in step S209, the station placement design unit 103 determines whether the number of generations has reached a predetermined number G (for example, 100). If the number of generations has not reached the predetermined number G, the station placement design unit 103 returns the process to step S204 and executes the same process again. On the other hand, if the number of generations has reached the predetermined number G, the station placement design unit 103 ends the process of FIG. 2.

[0042] The processing of steps S203 to S210 in FIG. 2 is a specific example of processing in which the station location design system 1 expresses the installation state of a base station as a binary value for each candidate point 303 for the installation location of the base station, prepares multiple candidates for the installation state of the base station for all candidate points 303, evaluates the candidates for the installation state of the base station using an objective function including the terminal coverage rate and the number of installed base stations, performs selection, crossover, and mutation processes using a genetic algorithm to proceed with generational change, and calculates the station location design result by updating the candidates for the installation state of the base station.

[0043] (Example of Result Display Screen) Fig. 6 is a diagram showing an example of a result display screen output by the station placement design system 1. In the example of Fig. 8, a result display screen 600 displays, on an xy coordinate system with x on the horizontal axis and y on the vertical axis, installation positions of base stations (BS) 601, terminals not covered by base stations (UE_uncovered) 602, and terminals covered by base stations (UE_covered) 603, as base station placement results.

[0044] Furthermore, the station placement design system 1 may display, as a status during design derivation (optimization progress status), the design result with the maximum objective function for each generation on the result display screen 600. Note that the result display screen 600 shown in Fig. 6 may be created by the station placement design device 100, or may be created and displayed by the terminal device 110 using the station placement design result acquired from the station placement design device 100.

[0045] (Application Example) In the above embodiment, the received signal strength at each installed terminal 302 is used as the criterion, but other criteria such as the signal-to-interference and noise ratio, the throughput, etc. may also be used. In this case, the station placement design system 1 can calculate estimated values ​​of the signal-to-interference and noise ratio, the throughput, etc. based on the received signal strength.

[0046] In the above embodiment, the number of base stations is used as an element of the objective function in the station placement design, but this is not limiting. For example, when designing a combination of multiple base stations with different equipment costs, it is possible to derive a station placement design result for a mixture of multiple models by using the total equipment cost instead of the number of base stations.

[0047] <Hardware Configuration> (Hardware Configuration of Station Placement Design Device) The station placement design device 100 and the terminal device 110 according to this embodiment have, for example, the hardware configuration of a computer 700 as shown in Fig. 7. Alternatively, the station placement design device 100 is realized by a plurality of computers 700.

[0048] 7 is a diagram showing an example of the hardware configuration of a computer according to this embodiment. In the example of Fig. 7, a computer 700 includes a processor 701, a memory 702, a storage device 703, a communication device 704, an input device 705, an output device 706, and a bus B.

[0049] The processor 701 is, for example, an arithmetic unit such as a CPU (Central Processing Unit) that executes predetermined programs to realize various functions. The memory 702 is a storage medium readable by the computer 700, and includes, for example, a RAM (Random Access Memory) and a ROM (Read Only Memory). The storage device 703 is a computer-readable storage medium, and may include, for example, a HDD (Hard Disk Drive), an SSD (Solid State Drive), various optical disks, and magneto-optical disks.

[0050] The communication device 704 includes one or more pieces of hardware (communication devices) for communicating with other devices via a wireless or wired network. The input device 705 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 706 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 705 and the output device 706 may be integrated into one device (e.g., an input / output device such as a touch panel display).

[0051] The bus B is commonly connected to the above components and transmits, for example, address signals, data signals, and various control signals. The processor 701 is not limited to a CPU, and may be, for example, a DSP (Digital Signal Processor), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array).

[0052] (Supplementary Note) The station location design device 100 in this embodiment is not limited to being realized by a dedicated device, but may also be realized by a general-purpose computer. In this case, a program for realizing this function may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be read into a computer system and executed to realize the function. Note that the term "computer system" here includes hardware such as an OS and peripheral devices.

[0053] Furthermore, "computer-readable recording media" includes various storage devices such as portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as hard disks built into computer systems. Furthermore, "computer-readable recording media" may also include devices that dynamically store programs for a short period of time, such as communication lines when transmitting programs via networks such as the Internet or communication lines such as telephone lines, and devices that store programs for a certain period of time, such as volatile memory within computer systems that serve as servers or clients in such cases.

[0054] Furthermore, the above program may be one that realizes part of the above-mentioned functions, or may be one that can realize the above-mentioned functions in combination with a program already recorded in a computer system, or may be one that is realized using hardware such as a PLD (Programmable Logic Device) or FPGA (Field Programmable Gate Array).

[0055] <Effects of the embodiment> A station placement design system can be provided that can appropriately place base stations throughout the entire wireless area and reduce the amount of calculation compared to a full search. For example, the station placement design system 1 according to the present embodiment can obtain a globally optimal solution compared to a greedy method (less likely to fall into a local solution) and can significantly reduce the amount of calculation compared to a full search.

[0056] Summary of Embodiments This specification discloses at least the following station placement design system, station placement design device, station placement design method, and program: (Item 1) A station placement design system that designs installation positions of base stations to build a wireless area, expressing the installation state of the base station with a binary value for each candidate point of the installation position of the base station and preparing multiple candidates for the installation state of the base station for all the candidate points, evaluating the candidates for the installation state of the base station using an objective function including a terminal coverage rate and the number of installed base stations, and performing generational change by adding processes of selection, crossover, and mutation using a genetic algorithm, and updating the candidates for the installation state of the base station to calculate a station placement design result. (Item 2) A station location design device that designs installation locations of base stations to build a wireless area, expressing an installation state of the base station for each candidate point for the installation location of the base station with a binary value, and preparing a plurality of candidate installation states of the base station for all candidate points, evaluating the candidate installation states of the base station with an objective function including a terminal coverage rate and the number of installed base stations, and performing generational change by adding selection, crossover, and mutation processes using a genetic algorithm, and updating the candidate installation states of the base station to calculate a station location design result. (Item 3) A station location design method that a computer that designs installation locations of base stations to build a wireless area, expressing an installation state of the base station for each candidate point for the installation location of the base station with a binary value, and preparing a plurality of candidate installation states of the base station for all candidate points, evaluating the candidate installation states of the base station with an objective function including a terminal coverage rate and the number of installed base stations, and performing generational change by adding selection, crossover, and mutation processes using a genetic algorithm, and updating the candidate installation states of the base station to calculate a station location design result. (4) A program that causes a computer to execute the station placement design method according to (3).

[0057] Although the present embodiment has been described above, the present invention is not limited to such a specific embodiment, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.

[0058] REFERENCE SIGNS LIST 1 Station placement design system 100 Station placement design device 110 Terminal device 101 Communication unit 102 Input / output unit 103 Station placement design unit 104 Storage unit 303 Candidate point 700 Computer

Claims

1. A station placement design system for designing the installation positions of base stations for constructing a wireless area, which represents the installation state of the base stations in binary for each candidate point of the installation positions of the base stations, prepares a plurality of candidates for the installation states of the base stations for all candidate points, evaluates the candidates for the installation states of the base stations with an objective function including the coverage rate of terminals and the number of installed base stations, advances generation alternation by applying selection, crossover, and mutation processes using a genetic algorithm, and calculates a station placement design result by performing an update process on the candidates for the installation states of the base stations.

2. A station placement design apparatus for designing the installation positions of base stations for constructing a wireless area, which represents the installation state of the base stations in binary for each candidate point of the installation positions of the base stations, prepares a plurality of candidates for the installation states of the base stations for all candidate points, evaluates the candidates for the installation states of the base stations with an objective function including the coverage rate of terminals and the number of installed base stations, advances generation alternation by applying selection, crossover, and mutation processes using a genetic algorithm, and calculates a station placement design result by performing an update process on the candidates for the installation states of the base stations.

3. A computer for designing the installation positions of base stations for constructing a wireless area, which represents the installation state of the base stations in binary for each candidate point of the installation positions of the base stations, prepares a plurality of candidates for the installation states of the base stations for all candidate points, evaluates the candidates for the installation states of the base stations with an objective function including the coverage rate of terminals and the number of installed base stations, advances generation alternation by applying selection, crossover, and mutation processes using a genetic algorithm, and calculates a station placement design result by performing an update process on the candidates for the installation states of the base stations.

4. A program for causing a computer to execute the station placement design method according to claim 3.

Images